Class: PDF::Reader::TextRun

Inherits:
Object
  • Object
show all
Includes:
Comparable
Defined in:
lib/pdf/reader/text_run.rb

Overview

A value object that represents one or more consecutive characters on a page.

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(x, y, width, font_size, text) ⇒ TextRun

Returns a new instance of TextRun.



17
18
19
20
21
22
 
# File 'lib/pdf/reader/text_run.rb', line 17

def initialize(x, y, width, font_size, text)
  @origin = PDF::Reader::Point.new(x, y)
  @width = width
  @font_size = font_size
  @text = text
end

Instance Attribute Details

#font_size ⇒ Object (readonly)

Returns the value of attribute font_size.



12
13
14
 
# File 'lib/pdf/reader/text_run.rb', line 12

def font_size
  @font_size
end

#origin ⇒ Object (readonly)

Returns the value of attribute origin.



10
11
12
 
# File 'lib/pdf/reader/text_run.rb', line 10

def origin
  @origin
end

#text ⇒ Object (readonly) Also known as: to_s

Returns the value of attribute text.



13
14
15
 
# File 'lib/pdf/reader/text_run.rb', line 13

def text
  @text
end

#width ⇒ Object (readonly)

Returns the value of attribute width.



11
12
13
 
# File 'lib/pdf/reader/text_run.rb', line 11

def width
  @width
end

Instance Method Details

#+(other) ⇒ Object

Raises:

  • (ArgumentError) 


64
65
66
67
68
69
70
71
72
 
# File 'lib/pdf/reader/text_run.rb', line 64

def +(other)
  raise ArgumentError, "#{other} cannot be merged with this run" unless mergable?(other)

  if (other.x - endx) <( font_size * 0.2)
    TextRun.new(x, y, other.endx - x, font_size, text + other.text)
  else
    TextRun.new(x, y, other.endx - x, font_size, "#{text} #{other.text}")
  end
end

#<=>(other) ⇒ Object

Allows collections of TextRun objects to be sorted. They will be sorted in order of their position on a cartesian plain - Top Left to Bottom Right



26
27
28
29
30
31
32
33
34
35
36
37
38
 
# File 'lib/pdf/reader/text_run.rb', line 26

def <=>(other)
  if x == other.x && y == other.y
    0
  elsif y < other.y
    1
  elsif y > other.y
    -1
  elsif x < other.x
    -1
  elsif x > other.x
    1
  end
end

#endx ⇒ Object 



48
49
50
 
# File 'lib/pdf/reader/text_run.rb', line 48

def endx
  @endx ||= @origin.x + width
end

#endy ⇒ Object 



52
53
54
 
# File 'lib/pdf/reader/text_run.rb', line 52

def endy
  @endy ||= @origin.y + font_size
end

#inspect ⇒ Object 



74
75
76
 
# File 'lib/pdf/reader/text_run.rb', line 74

def inspect
  "#{text} w:#{width} f:#{font_size} @#{x},#{y}"
end

#intersect?(other_run) ⇒ Boolean

Returns:

  • (Boolean) 


78
79
80
81
 
# File 'lib/pdf/reader/text_run.rb', line 78

def intersect?(other_run)
  x <= other_run.endx && endx >= other_run.x &&
    endy >= other_run.y && y <= other_run.endy
end

#intersection_area_percent(other_run) ⇒ Object

return what percentage of this text run is overlapped by another run



84
85
86
87
88
89
90
91
92
 
# File 'lib/pdf/reader/text_run.rb', line 84

def intersection_area_percent(other_run)
  return 0 unless intersect?(other_run)

  dx = [endx, other_run.endx].min - [x, other_run.x].max
  dy = [endy, other_run.endy].min - [y, other_run.y].max
  intersection_area = dx*dy

  intersection_area.to_f / area
end

#mean_character_width ⇒ Object 



56
57
58
 
# File 'lib/pdf/reader/text_run.rb', line 56

def mean_character_width
  @width / character_count
end

#mergable?(other) ⇒ Boolean

Returns:

  • (Boolean) 


60
61
62
 
# File 'lib/pdf/reader/text_run.rb', line 60

def mergable?(other)
  y.to_i == other.y.to_i && font_size == other.font_size && mergable_range.include?(other.x)
end

#x ⇒ Object 



40
41
42
 
# File 'lib/pdf/reader/text_run.rb', line 40

def x
  @origin.x
end

#y ⇒ Object 



44
45
46
 
# File 'lib/pdf/reader/text_run.rb', line 44

def y
  @origin.y
end